Fault determination method and corresponding device for fan bearing box of thermal power plant

Abstract

The invention relates to a fault determination method and device for a fan bearing box of a thermal power plant, and the method comprises the steps: determining the vibration data of the fan bearing box of the thermal power plant, and enabling the vibration data to be used for representing the vibration amplitude data of the fan bearing box in the operation process; performing spectrum analysis processing on the vibration data to obtain spectrum data; and determining a target vibration frequency in the frequency spectrum data, and determining target fault information of the fan bearing box at least according to the target vibration frequency. The target fault information is determined according to the vibration data of the fan bearing box, the accuracy of the target fault information can be improved, and meanwhile the precision of the target fault information can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method for determining a fault of a fan bearing box in a thermal power plant and a corresponding device. Background Art

[0002] The fan bearing box is an important component used to ensure the operating efficiency and service life of the fan. When the fan bearing box fails, the fan operating efficiency and service life will be reduced. In the related technology, the fan bearing box is monitored by the DCS system (Distributed Control System). However, when the fan bearing box is monitored by the DCS system, only two types of fault information, namely, the vibration exceeding the standard alarm value and the protection trip value, are displayed on the interface, which may reduce the accuracy of determining the fault information of the fan bearing box. Summary of the invention

[0003] The purpose of the present disclosure is to provide a method for determining a fault of a fan bearing box in a thermal power plant and a corresponding device to solve the technical problems existing in the related art.

[0004] In order to achieve the above objectives, in a first aspect, the present disclosure provides a method for determining a fault of a fan bearing box in a thermal power plant, the method comprising: Determine vibration data on a bearing box of a fan in a thermal power plant, wherein the vibration data is used to characterize amplitude data of vibration of the bearing box of the fan during operation; Performing spectrum analysis on the vibration data to obtain spectrum data; A target vibration frequency in the frequency spectrum data is determined, and target fault information of the fan bearing box is determined at least based on the target vibration frequency.

[0005] Optionally, determining target fault information of the fan bearing box at least according to the target vibration frequency includes: The target fault type of the fan bearing box is determined according to the target vibration frequency and a first preset fault relationship, wherein the first preset fault relationship is used to characterize the relationship between the fault type and the vibration frequency of the fan bearing box.

[0006] Optionally, determining target fault information of the fan bearing box at least according to the target vibration frequency includes: Processing the target vibration frequency by an impact demodulation method to obtain equipment damage fault information of the fan bearing box; or, Determining image information of each device on the fan bearing box; Extracting first feature data from the image information, where the first feature data is used to characterize the status of each device on the fan bearing box; Extracting second characteristic data from the target vibration frequency, wherein the second characteristic data is used to characterize the operating characteristics of each device on the fan bearing box; The first characteristic data and the second characteristic data are processed by a machine learning method to obtain equipment damage fault information of the fan bearing box.

[0007] Optionally, the method further comprises: Determining target operating parameters of the fan bearing box; The step of determining target fault information of the fan bearing box at least according to the target vibration frequency includes: The target fault cause of the fan bearing box is determined based on the target operating parameters, the target vibration frequency and the second preset fault relationship, wherein the second preset fault relationship is used to characterize the relationship between the operating parameter data and the vibration frequency of the fan bearing box, and each vibration frequency is associated with a fault cause.

[0008] Optionally, the method further comprises: In response to an import operation for the target fault information in a fan bearing box model, the target fault information corresponding to the import operation is displayed in the fan bearing box model, wherein the fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner; or The target fault information is input into a target life prediction model to obtain a target predicted life of the fan bearing box, wherein the target life prediction model is obtained by training a normal distribution model with historical fault information.

[0009] Optionally, the target life prediction model is expressed by the following calculation formula:

[0010] in, predicting the lifetime for the target, is the rated life of the fan bearing housing, is the lubricating oil viscosity ratio of the fan bearing box, is the particle size ratio of the lubricating oil of the fan bearing box, is the operating time of the fan bearing box, is the difference between the rated temperature of the fan bearing box and the inlet oil temperature, is the difference between the operating temperature of the fan bearing housing and the inlet oil temperature, is the number of times the operating temperature of the fan bearing box in the target fault information exceeds the rated temperature, is the difference between the rated vibration frequency and the average vibration frequency of the fan bearing box, is the difference between the target vibration frequency and the average vibration frequency of the fan bearing box, is the acceleration rate constant of the fan bearing box in the target fault information during operation, is the difference between the rated current and the average current of the fan bearing box, is the difference between the operating current and the average current of the fan bearing box, is the rated number of times that the operating current of the fan bearing box in the target fault information exceeds the rated current, is the starting coefficient of the fan bearing box.

[0011] In a second aspect, the present disclosure provides a fault determination device for a fan bearing box in a thermal power plant, comprising a first determination module, a processing module, and a second determination module; The first determination module is used to determine vibration data on the bearing box of the fan in the thermal power plant, and the vibration data is used to characterize the amplitude data of the vibration of the bearing box of the fan during operation; The processing module is used to perform spectrum analysis on the vibration data to obtain spectrum data; The second determination module is used to determine a target vibration frequency in the frequency spectrum data, and determine target fault information on the fan bearing box at least based on the target vibration frequency.

[0012] Optionally, the second determining module is used to: The target fault type of the fan bearing box is determined according to the target vibration frequency and a first preset fault relationship, wherein the first preset fault relationship is used to characterize the relationship between the fault type and the vibration frequency of the fan bearing box.

[0013] Optionally, the second determining module includes: A first processing submodule is used to process the target vibration frequency by an impact demodulation method to obtain equipment damage fault information of the fan bearing box; A third determination module is used to determine the image information of each device on the fan bearing box; A first feature extraction module, used to extract first feature data from the image information, wherein the first feature data is used to characterize the state of each device on the fan bearing box; A second feature extraction module, used to extract second feature data from the target vibration frequency, wherein the second feature data is used to characterize the operating characteristics of each device on the fan bearing box; The second processing submodule is used to process the first characteristic data and the second characteristic data by a machine learning method to obtain equipment damage fault information of the fan bearing box.

[0014] Optionally, the device further comprises: A fourth determination module, used to determine target operating parameters of the fan bearing box; The second determining module is used for: The target fault cause of the fan bearing box is determined based on the target operating parameters, the target vibration frequency and the second preset fault relationship, wherein the second preset fault relationship is used to characterize the relationship between the operating parameter data and the vibration frequency of the fan bearing box, and each vibration frequency is associated with a fault cause.

[0015] Optionally, the device further comprises: A display module, configured to, in response to an import operation for the target fault information in a fan bearing box model, display the target fault information corresponding to the import operation in the fan bearing box model, wherein the fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner; The prediction module is used to input the target fault information into a target life prediction model to obtain the target predicted life of the fan bearing box, wherein the target life prediction model is obtained by training a normal distribution model with historical fault information.

[0016] Optionally, the target life prediction model is expressed by the following calculation formula:

[0017] in, predicting the lifetime for the target, is the rated life of the fan bearing housing, is the lubricating oil viscosity ratio of the fan bearing box, is the particle size ratio of the lubricating oil of the fan bearing box, is the operating time of the fan bearing box, is the difference between the rated temperature of the fan bearing box and the inlet oil temperature, is the difference between the operating temperature of the fan bearing housing and the inlet oil temperature, is the number of times the operating temperature of the fan bearing box in the target fault information exceeds the rated temperature, is the difference between the rated vibration frequency and the average vibration frequency of the fan bearing box, is the difference between the target vibration frequency and the average vibration frequency of the fan bearing box, is the acceleration rate constant of the fan bearing box in the target fault information during operation, is the difference between the rated current and the average current of the fan bearing box, is the difference between the operating current and the average current of the fan bearing box, is the rated number of times that the operating current of the fan bearing box in the target fault information exceeds the rated current, is the starting coefficient of the fan bearing box.

[0018] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present disclosure.

[0019] In a fourth aspect, the present disclosure provides a fault determination device for a fan bearing box of a thermal power plant, comprising: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods provided in the first aspect of the present disclosure.

[0020] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the methods provided in the first aspect of the present disclosure.

[0021] Through the above technical solution, by performing spectrum processing on the vibration data on the fan bearing box of the thermal power plant, spectrum data is obtained, and then at least the target fault information in the fan bearing box can be determined according to the target vibration frequency in the spectrum data. Among them, the vibration data can be used to characterize the amplitude data of the vibration of the fan bearing box during operation. Determining the target fault information based on the vibration data of the fan bearing box can improve the accuracy of the target fault information and at the same time improve the precision of the target fault information.

[0022] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The diagram is a schematic diagram showing a method for determining a fault of a fan bearing box in a thermal power plant according to an exemplary embodiment of the present disclosure.

[0024] Figure 2 FIG. 4 is a schematic diagram showing a vibration data acquisition device according to an exemplary embodiment of the present disclosure.

[0025] Figure 3 is a schematic diagram showing a wind turbine bearing box model according to an exemplary embodiment of the present disclosure.

[0026] Figure 4 It is a schematic diagram showing display screen display according to an exemplary embodiment of the present disclosure.

[0027] Figure 5 The diagram is a schematic diagram showing a device for determining a fault of a fan bearing box in a thermal power plant according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0029] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0030] With the popularization and application of information systems such as ERP (Enterprise Resource Planning), EAM (Enterprise Asset Management) and SIS (Safety Instrumented System) in enterprises, enterprises have accumulated a large amount of business process data such as equipment defects, fault repairs, and maintenance records in long-term equipment management activities, and the on-site real-time monitoring system has also accumulated a large amount of historical real-time data. These data provide a rich data foundation for enterprises to carry out big data mining and deeply practice various equipment analysis and evaluation methods, and lay a certain data foundation for giving full play to big data collaboration, effectively reducing personnel workload, and realizing component-level fault modeling, intelligent fault diagnosis and analysis, and equipment health evaluation of major equipment in power enterprises.

[0031] As an important auxiliary equipment in thermal power plants, fans are responsible for the important task of transporting air and other fluids to ensure the normal operation of the units. In particular, fans such as forced draft fans, induced draft fans and primary fans are in a state of large flow and high wind pressure operation for a long time. With the increase of peak-shaving tasks of the units, the operating conditions of fans change frequently. The operating conditions of equipment such as fan shaft systems, moving and stationary blades, motors, and hydraulic couplings need to be monitored more closely. Conventional maintenance modes have been difficult to adapt to the new power generation business model.

[0032] The fan bearing box in the fan is an important device that affects the operating efficiency and service life of the fan. Therefore, it is necessary to use advanced technologies such as artificial intelligence and big data to perceive the operating status of the fan bearing box in real time and monitor the operating status of the fan bearing box in real time.

[0033] In the related art, the fan bearing box is usually monitored in real time through the DCS system. However, when the fan bearing box is monitored in real time through the DCS system, only two fault information, namely, the vibration exceeding alarm value output and the protection trip value output, are displayed on the DCS system interface. It is unable to process other data, and thus is unable to detect other faults occurring in the fan bearing box, thereby reducing the accuracy of determining the fault information of the fan bearing box. In severe cases, it may cause the fan to stop or reduce load.

[0034] In view of this, the present disclosure provides a fault determination method and corresponding device for a fan bearing box in a thermal power plant to solve the technical problems existing in the above-mentioned related technologies.

[0035] like Figure 1 As shown, Figure 1 is a schematic diagram showing a method for determining a fault of a fan bearing box in a thermal power plant according to an exemplary embodiment of the present disclosure, with reference to Figure 1 ,include: S101: Determine vibration data on a bearing box of a fan in a thermal power plant, where the vibration data is used to characterize amplitude data of vibration of the bearing box of the fan during operation; S102: Performing spectrum analysis on the vibration data to obtain spectrum data; S103: Determine a target vibration frequency in the frequency spectrum data, and determine target fault information of the fan bearing box at least based on the target vibration frequency.

[0036] Through the above technical solution, by performing spectrum processing on the vibration data on the fan bearing box of the thermal power plant, spectrum data is obtained, and then at least the target fault information in the fan bearing box can be determined according to the target vibration frequency in the spectrum data. Among them, the vibration data can be used to characterize the amplitude data of the vibration of the fan bearing box during operation. Determining the target fault information based on the vibration data of the fan bearing box can improve the accuracy of the target fault information and at the same time improve the precision of the target fault information.

[0037] In order to enable those skilled in the art to better understand the method for determining the fault of a fan bearing box in a thermal power plant provided by the present disclosure, the above steps are described in detail with examples below.

[0038] For example, a thermal power plant is an industrial facility that can be used to convert the chemical energy of fossil fuels into electrical energy.

[0039] Vibration data can be used to characterize the amplitude data of the vibration generated by the fan bearing box during operation. The vibration data can be data in one direction or multiple sets of data in different directions. In this embodiment, the vibration data can be obtained through a vibration sensor. The vibration sensor can be set as one or more. When multiple vibration sensors are set, the multiple vibration sensors can be respectively set in different directions of the fan bearing box, and then the vibration data of the fan bearing box in different directions can be obtained through the vibration sensor. For example, Figure 2 As shown, four vibration sensors 1 can be installed on the motor side of the fan, three vibration sensors 1 can be installed on the bearing box of a single-stage fan, and four vibration sensors 1 can be installed on the bearing box of a double-stage fan. Afterwards, the offline vibration data collector 3 can collect vibration data on the vibration sensor through the terminal board 2. This is not specifically limited in the embodiments of the present disclosure.

[0040] For example, after obtaining the vibration data on the fan bearing box, the vibration data can be subjected to spectrum analysis to obtain spectrum data. Spectrum analysis can be an analysis method for decomposing a signal into component frequency components. The process of performing spectrum analysis on the vibration data can be to analyze and process the vibration data using a spectrum analysis processing method in the related art, which will not be described in detail in this disclosure.

[0041] For example, the target fault information may include at least one of the fault type, fault cause, and equipment damage fault information on the fan bearing box, and the embodiments of the present disclosure do not specifically limit this. After the spectrum data is obtained, the target fault information of the fan bearing box can be determined by the target vibration frequency in the spectrum data. The target vibration frequency may be the vibration frequency of the fan bearing box during operation.

[0042] In a possible manner, determining target fault information of the wind turbine bearing box at least according to the target vibration frequency includes: The target fault type of the fan bearing box is determined according to the target vibration frequency and a first preset fault relationship, wherein the first preset fault relationship is used to characterize the relationship between the fault type and the vibration frequency of the fan bearing box.

[0043] It should be understood that the fault type may be a bearing wear fault, a bearing damage fault, a fan bearing box lubricating oil fault, etc. The target fault information may include a target fault type. When a certain fault type occurs in the fan bearing box during operation, a vibration frequency corresponding to the fault type may be generated, that is, different fault types may correspond to different vibration frequencies. Furthermore, when determining the target fault information of the fan bearing box according to the target vibration frequency, the target fault type may be determined according to the target vibration frequency and the first preset fault relationship. Among them, the first preset fault relationship may characterize the relationship between the fault type and the vibration frequency.

[0044] In a possible manner, determining target fault information of the wind turbine bearing box at least according to the target vibration frequency includes: Processing the target vibration frequency by an impact demodulation method to obtain equipment damage fault information of the fan bearing box; or, Determining image information of each device on the fan bearing box; Extracting first feature data from the image information, where the first feature data is used to characterize the status of each device on the fan bearing box; Extracting second characteristic data from the target vibration frequency, wherein the second characteristic data is used to characterize the operating characteristics of each device on the fan bearing box; The first characteristic data and the second characteristic data are processed by a machine learning method to obtain equipment damage fault information of the fan bearing box.

[0045] It should be understood that the target fault information may also include equipment damage fault information. When the equipment damage fault information is determined according to the target vibration frequency, the equipment damage fault information may be obtained by processing the target vibration frequency through an impact demodulation method, or by processing the image information on the fan bearing box and the target vibration frequency, and the equipment damage fault information may be obtained. This is not specifically limited in the embodiments of the present disclosure.

[0046] The impact demodulation method can be used to detect and diagnose faults caused by impact or collision. When the target vibration frequency is processed by the impact demodulation method, the target vibration frequency can be amplified first, and then the amplified target frequency signal containing the fault feature point is extracted by a bandpass filter, and then the impact signal in the target frequency signal is extracted by the impact demodulation method, and the impact signal is analyzed by short-time Fourier transform to obtain equipment damage fault information. Among them, the equipment damage fault information can be information about cracks in the equipment, information about fractures in the equipment, and other fault information. Processing the target vibration frequency by the impact demodulation method can improve the accuracy of determining the target fault information.

[0047] Image information can be acquired through a camera device. And the camera device can be one or two. When there are two cameras, the two cameras can be respectively set above and below the fan bearing box. Afterwards, the first feature data in the image information can be extracted, and the first feature data can characterize the status of each device of the fan bearing box, wherein the status of the device can be the state of oil leakage of the device, the state of cracks in the device, and the state of fracture of the device, to which the embodiment of the present disclosure does not make specific restrictions. Afterwards, the second feature data in the target vibration frequency can be extracted, and the second feature data can be used to characterize the operating characteristics of each device of the fan bearing box. Among them, the operating characteristics of the equipment may include abnormal temperature characteristics of the equipment, abnormal load characteristics of the equipment, and abnormal current signal characteristics of the equipment, to which the embodiment of the present disclosure does not make specific restrictions. Afterwards, the first feature data and the second feature data can be processed by a machine learning method to obtain equipment damage fault information of the fan bearing box. Among them, the machine learning method can be a support vector machine method or a model training method, to which the embodiment of the present disclosure does not make specific restrictions.

[0048] By processing the target vibration frequency, or processing the image information and the target vibration frequency, the equipment damage fault information can be obtained, and the accuracy of the equipment damage fault information can be improved.

[0049] In a possible embodiment, the method further comprises: Determining target operating parameters of the fan bearing box; The step of determining target fault information of the fan bearing box at least according to the target vibration frequency includes: The target fault cause of the fan bearing box is determined based on the target operating parameters, the target vibration frequency and the second preset fault relationship, wherein the second preset fault relationship is used to characterize the relationship between the operating parameter data and the vibration frequency of the fan bearing box, and each vibration frequency is associated with a fault cause.

[0050] It should be understood that the target operating parameters may be the temperature, current signal, voltage signal and load of the fan bearing box during operation, and the present disclosure does not specifically limit this. After determining the target operating parameters, the target fault information may also be determined based on the target operating parameters and the target vibration frequency.

[0051] The target fault information may include the cause of the fault. The target fault cause of the fan bearing box may then be determined based on the target operating parameters, the target vibration frequency, and the second preset fault relationship. Among them, the second preset fault relationship may be the relationship between the operating parameters and the vibration frequency, and each vibration frequency corresponds to a fault cause. That is to say, in the second preset fault relationship, each vibration frequency corresponds to a specific fault type, and also corresponds to the fault cause that generates the fault type. The fault cause may be a temperature abnormality cause, a current abnormality cause, or a load abnormality cause, and the embodiments of the present disclosure do not make specific limitations on this.

[0052] In a possible embodiment, the method further comprises: In response to an import operation for the target fault information in a fan bearing box model, the target fault information corresponding to the import operation is displayed in the fan bearing box model, wherein the fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner; or The target fault information is input into a target life prediction model to obtain a target predicted life of the fan bearing box, wherein the target life prediction model is obtained by training a normal distribution model with historical fault information.

[0053] It should be understood that after the target fault information is generated, the target fault information can be imported into the fan bearing box model and displayed in the fan bearing box model. The fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner, and the three-dimensional bearing box model can be displayed on a three-dimensional platform built with the Unity 3D (real-time three-dimensional interactive content creation and operation platform) engine. The three-dimensional laser scanner can be a high-precision measuring device, which mainly captures the shape and size of the object to build a three-dimensional model of the object by emitting a laser beam and measuring the time or angle of reflection. For example, Figure 3 As shown, a fan bearing box model can be constructed, and operating parameters can be displayed in real time on the fan bearing box model, including current, speed, valve opening, vibration, inlet parameters, outlet parameters, B1 segment parameters, B2 segment parameters, B3 segment parameters and B4 segment parameters, and segments B1-B4 correspond to different segments of the fan bearing box. Figure 3 It can be intuitively seen that if one of the parameter data in the B3 segment changes from white to red, it can represent that the target fault information of the fan bearing box appears in the B3 segment.

[0054] After obtaining the target fault information, the life of the fan bearing box can be predicted according to the target fault information. The target predicted life of the fan bearing box can be obtained by inputting the target fault information into the target life prediction model. The target life prediction model can be obtained by training a normal distribution model with historical fault information.

[0055] In a possible way, the target life prediction model is expressed by the following calculation formula:

[0056] in, predicting the lifetime for the target, is the rated life of the fan bearing housing, is the lubricating oil viscosity ratio of the fan bearing box, is the particle size ratio of the lubricating oil of the fan bearing box, is the operating time of the fan bearing box, is the difference between the rated temperature of the fan bearing box and the inlet oil temperature, is the difference between the operating temperature of the fan bearing housing and the inlet oil temperature, is the number of times the operating temperature of the fan bearing box in the target fault information exceeds the rated temperature, is the difference between the rated vibration frequency and the average vibration frequency of the fan bearing box, is the difference between the target vibration frequency and the average vibration frequency of the fan bearing box, is the acceleration rate constant of the fan bearing box in the target fault information during operation, is the difference between the rated current and the average current of the fan bearing box, is the difference between the operating current and the average current of the fan bearing box, is the rated number of times that the operating current of the fan bearing box in the target fault information exceeds the rated current, is the starting coefficient of the fan bearing box.

[0057] In another possible manner, target fault information, vibration data, target operating parameters, and corresponding maintenance suggestions occurring on the fan bearing box may also be displayed on the display screen. Figure 4As shown, the display screen includes health status, communication status, collected vibration data and corresponding time, main parameters, fan energy efficiency and fan bearing box model, among which the health status can display target fault information and maintenance suggestions for handling the target fault information, and the target fault information includes diagnosis and analysis of the corresponding motor free end bearing wear. The corresponding maintenance suggestions can be the motor maintenance plan to build the operation instructions H1. The main parameters can be the target operating parameters. According to Figure 4 The displayed image can intuitively show the target fault information of the fan bearing box and the corresponding maintenance suggestions.

[0058] Through the above technical solution, the target fault information of the fan bearing box is determined according to the vibration data, target operating parameters and image information of the fan bearing box, and in combination with the first preset fault relationship and the second preset fault relationship, so that the accuracy of the target fault information and the precision of the target fault information can be improved. By displaying the target fault information on the fan bearing box model in real time, the user can intuitively understand the target fault information of the fan bearing box. And according to the target fault information, the service life of the fan bearing box can be predicted.

[0059] Based on the same concept, this embodiment also discloses a fault determination device for a fan bearing box in a thermal power plant, referring to Figure 5 , Figure 5 FIG. 1 is a schematic diagram showing a fault determination device for a fan bearing box of a thermal power plant according to an exemplary embodiment of the present disclosure. Figure 5 As shown, it includes a first determining module, a processing module and a second determining module; The first determination module is used to determine vibration data on the bearing box of the fan in the thermal power plant, and the vibration data is used to characterize the amplitude data of the vibration of the bearing box of the fan during operation; The processing module is used to perform spectrum analysis on the vibration data to obtain spectrum data; The second determination module is used to determine a target vibration frequency in the frequency spectrum data, and determine target fault information on the fan bearing box at least based on the target vibration frequency.

[0060] Optionally, the second determining module is used to: The target fault type of the fan bearing box is determined according to the target vibration frequency and a first preset fault relationship, wherein the first preset fault relationship is used to characterize the relationship between the fault type and the vibration frequency of the fan bearing box.

[0061] Optionally, the second determining module includes: A first processing submodule is used to process the target vibration frequency by an impact demodulation method to obtain equipment damage fault information of the fan bearing box; A third determination module is used to determine the image information of each device on the fan bearing box; A first feature extraction module, used to extract first feature data from the image information, wherein the first feature data is used to characterize the state of each device on the fan bearing box; A second feature extraction module, used to extract second feature data from the target vibration frequency, wherein the second feature data is used to characterize the operating characteristics of each device on the fan bearing box; The second processing submodule is used to process the first characteristic data and the second characteristic data by a machine learning method to obtain equipment damage fault information of the fan bearing box.

[0062] Optionally, the device further comprises: A fourth determination module, used to determine target operating parameters of the fan bearing box; The second determining module is used for: The target fault cause of the fan bearing box is determined based on the target operating parameters, the target vibration frequency and the second preset fault relationship, wherein the second preset fault relationship is used to characterize the relationship between the operating parameter data and the vibration frequency of the fan bearing box, and each vibration frequency is associated with a fault cause.

[0063] Optionally, the device further comprises: A display module, configured to, in response to an import operation for the target fault information in a fan bearing box model, display the target fault information corresponding to the import operation in the fan bearing box model, wherein the fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner; The prediction module is used to input the target fault information into a target life prediction model to obtain the target predicted life of the fan bearing box, wherein the target life prediction model is obtained by training a normal distribution model with historical fault information.

[0064] Optionally, the target life prediction model is expressed by the following calculation formula:

[0065] in, predicting the lifetime for the target, is the rated life of the fan bearing housing, is the lubricating oil viscosity ratio of the fan bearing box, is the particle size ratio of the lubricating oil of the fan bearing box, is the operating time of the fan bearing box, is the difference between the rated temperature of the fan bearing box and the inlet oil temperature, is the difference between the operating temperature of the fan bearing housing and the inlet oil temperature, is the number of times the operating temperature of the fan bearing box in the target fault information exceeds the rated temperature, is the difference between the rated vibration frequency and the average vibration frequency of the fan bearing box, is the difference between the target vibration frequency and the average vibration frequency of the fan bearing box, is the acceleration rate constant of the fan bearing box in the target fault information during operation, is the difference between the rated current and the average current of the fan bearing box, is the difference between the operating current and the average current of the fan bearing box, is the rated number of times that the operating current of the fan bearing box in the target fault information exceeds the rated current, is the starting coefficient of the fan bearing box.

[0066] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0067] Based on the same concept, the present embodiment also discloses a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for determining the fault of a fan bearing box in a thermal power plant disclosed in the present embodiment are implemented.

[0068] Based on the same concept, this embodiment also discloses a fault determination device for a fan bearing box of a thermal power plant, comprising: a memory having a computer program stored thereon; The processor is used to execute the computer program in the memory to implement the steps of the method for determining the fault of the fan bearing box of a thermal power plant disclosed in this embodiment.

[0069] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned fault determination method for a bearing box of a fan in a thermal power plant when executed by the programmable device.

[0070] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0071] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0072] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A method for determining a fault of a fan bearing box in a thermal power plant, characterized in that: Methods include: Determine vibration data on a bearing box of a fan in a thermal power plant, wherein the vibration data is used to characterize amplitude data of vibration of the bearing box of the fan during operation; Performing spectrum analysis on the vibration data to obtain spectrum data; A target vibration frequency in the frequency spectrum data is determined, and target fault information of the fan bearing box is determined at least based on the target vibration frequency.

2. The method for determining the fault of the fan bearing box of a thermal power plant according to claim 1, characterized in that: The step of determining target fault information of the fan bearing box at least according to the target vibration frequency includes: The target fault type of the fan bearing box is determined according to the target vibration frequency and a first preset fault relationship, wherein the first preset fault relationship is used to characterize the relationship between the fault type and the vibration frequency of the fan bearing box.

3. The method for determining the fault of a fan bearing box in a thermal power plant according to claim 1, characterized in that: The step of determining target fault information of the fan bearing box at least according to the target vibration frequency includes: Processing the target vibration frequency by an impact demodulation method to obtain equipment damage fault information of the fan bearing box; or, Determining image information of each device on the fan bearing box; Extracting first feature data from the image information, where the first feature data is used to characterize the status of each device on the fan bearing box; Extracting second characteristic data from the target vibration frequency, wherein the second characteristic data is used to characterize the operating characteristics of each device on the fan bearing box; The first characteristic data and the second characteristic data are processed by a machine learning method to obtain equipment damage fault information of the fan bearing box.

4. The method for determining the fault of a fan bearing box in a thermal power plant according to claim 1, characterized in that: The method further comprises: Determining target operating parameters of the fan bearing box; The step of determining target fault information of the fan bearing box at least according to the target vibration frequency includes: The target fault cause of the fan bearing box is determined based on the target operating parameters, the target vibration frequency and the second preset fault relationship, wherein the second preset fault relationship is used to characterize the relationship between the operating parameter data and the vibration frequency of the fan bearing box, and each vibration frequency is associated with a fault cause.

5. The method for determining the fault of a fan bearing box in a thermal power plant according to any one of claims 1 to 4, characterized in that: The method further comprises: In response to an import operation for the target fault information in a fan bearing box model, the target fault information corresponding to the import operation is displayed in the fan bearing box model, wherein the fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner; or The target fault information is input into a target life prediction model to obtain a target predicted life of the fan bearing box, wherein the target life prediction model is obtained by training a normal distribution model with historical fault information.

6. The method for determining the fault of a fan bearing box in a thermal power plant according to claim 5, characterized in that: The target life prediction model is expressed by the following calculation formula: in, predicting the lifetime for the target, is the rated life of the fan bearing housing, is the lubricating oil viscosity ratio of the fan bearing box, is the particle size ratio of the lubricating oil of the fan bearing box, is the operating time of the fan bearing box, is the difference between the rated temperature of the fan bearing box and the inlet oil temperature, is the difference between the operating temperature of the fan bearing housing and the inlet oil temperature, is the number of times the operating temperature of the fan bearing box in the target fault information exceeds the rated temperature, is the difference between the rated vibration frequency and the average vibration frequency of the fan bearing box, is the difference between the target vibration frequency and the average vibration frequency of the fan bearing box, is the acceleration rate constant of the fan bearing box in the target fault information during operation, is the difference between the rated current and the average current of the fan bearing box, is the difference between the operating current and the average current of the fan bearing box, is the rated number of times that the operating current of the fan bearing box in the target fault information exceeds the rated current, is the starting coefficient of the fan bearing box.

7. A device for determining a fault of a fan bearing box in a thermal power plant, characterized in that: It includes a first determining module, a processing module and a second determining module; The first determination module is used to determine vibration data on the bearing box of the fan in the thermal power plant, and the vibration data is used to characterize the amplitude data of the vibration of the bearing box of the fan during operation; The processing module is used to perform spectrum analysis on the vibration data to obtain spectrum data; The second determination module is used to determine a target vibration frequency in the frequency spectrum data, and determine target fault information on the fan bearing box at least based on the target vibration frequency.

8. The fault determination device for a fan bearing box in a thermal power plant according to claim 7, characterized in that: The second determining module is used for: The target fault type of the fan bearing box is determined according to the target vibration frequency and a first preset fault relationship, wherein the first preset fault relationship is used to characterize the relationship between the fault type and the vibration frequency of the fan bearing box.

9. The fault determination device for a fan bearing box in a thermal power plant according to claim 7, characterized in that: The second determining module comprises: A first processing submodule is used to process the target vibration frequency by an impact demodulation method to obtain equipment damage fault information of the fan bearing box; A third determination module is used to determine the image information of each device on the fan bearing box; A first feature extraction module, used to extract first feature data from the image information, wherein the first feature data is used to characterize the state of each device on the fan bearing box; A second feature extraction module, used to extract second feature data from the target vibration frequency, wherein the second feature data is used to characterize the operating characteristics of each device on the fan bearing box; The second processing submodule is used to process the first characteristic data and the second characteristic data by a machine learning method to obtain equipment damage fault information of the fan bearing box.

10. The fault determination device for a fan bearing box of a thermal power plant according to claim 7, characterized in that: The device also includes: A fourth determination module, used to determine target operating parameters of the fan bearing box; The second determining module is used for: The target fault cause of the fan bearing box is determined based on the target operating parameters, the target vibration frequency and the second preset fault relationship, wherein the second preset fault relationship is used to characterize the relationship between the operating parameter data and the vibration frequency of the fan bearing box, and each vibration frequency is associated with a fault cause.

11. The device for determining the fault of a fan bearing box in a thermal power plant according to any one of claims 7 to 10, characterized in that: The device also includes: A display module, configured to, in response to an import operation for the target fault information in a fan bearing box model, display the target fault information corresponding to the import operation in the fan bearing box model, wherein the fan bearing box model is obtained by scanning the fan bearing box with a three-dimensional laser scanner; The prediction module is used to input the target fault information into a target life prediction model to obtain the target predicted life of the fan bearing box, wherein the target life prediction model is obtained by training a normal distribution model with historical fault information.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

13. A fault determination device for a fan bearing box in a thermal power plant, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images